INDEX

Explanations

phrases indicating importance or significance in a narrative context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ayne

-0.17

osg

-0.17

ibt

-0.16

ç©´

-0.15

otti

-0.15

esses

-0.15

 JsonSerializer

-0.15

CTL

-0.14

 Wheeler

-0.14

ardy

-0.13

POSITIVE LOGITS

Ron

0.31

McG

0.27

Mal

0.25

 Moody

0.25

 Herm

0.24

 Sirius

0.24

Ron

0.24

 Neville

0.23

Ton

0.23

 Luna

0.23

Activations Density 0.001%

phrases indicating importance or significance in a narrative context

No Comments

No Known Activations